shovelingpig/awesome-ml-papers

Awesome Machine Learning Papers

Awesome Machine Learning Papers

Contributing

markdown format:

**Here is the Paper Name.**<br>
*[Author 1](homepage), Author 2, and Author 3.*<br>
Conference or Journal Year. [[PDF](link)] [[Project](link)] [[Github](link)] [[Video](link)] [[Data](link)]

CNN

• (ResNet) Deep Residual Learning for Image Recognition

RNN

• (GRU) Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling

Transformer

• (Transformer) Attention Is All You Need
• (ViT) An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Swin Transformer: Hierarchical Vision Transformer using Shifted Windows

AE

• (VAE) Auto-Encoding Variational Bayes

GAN

• (GAN) Generative Adversarial Networks
• (ProgressiveGAN) Progressive Growing of GANs for Improved Quality, Stability, and Variation
• (StyleGAN) A Style-Based Generator Architecture for Generative Adversarial Networks
• (StyleGAN2) Analyzing and Improving the Image Quality of StyleGAN
• (StyleGAN2-Ada) Training Generative Adversarial Networks with Limited Data
• (StyleGAN3) Alias-Free Generative Adversarial Networks
• StyleGAN-V: A Continuous Video Generator with the Price, Image Quality and Perks of StyleGAN2

Flow

• (Normalizing Flow) Variational Inference with Normalizing Flows
• Glow: Generative Flow with Invertible 1x1 Convolutions

Diffusion

• (DDPM) Diffusion Models Beat GANs on Image Synthesis

3DMM

3D Morphable Model

• (BFM) Morphable Face Models - An Open Framework
• (FLAME) Learning a model of facial shape and expression from 4D scans
• SMPL: A Skinned Multi-Person Linear Model

NeRF

Neural Radiance Field

• NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
• (Instant-NDP) Instant Neural Graphics Primitives with a Multiresolution Hash Encoding
• (DietNeRF) Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesis
• Point-NeRF: Point-based Neural Radiance Fields
• StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generation
• A-NeRF: Articulated Neural Radiance Fields for Learning Human Shape, Appearance, and Pose

Normalization

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Layer Normalization

Representation Learning

• Retriever: Learning Content-Style Representation as a Token-Level Bipartite Graph

Contrastive Learning

• (SimCLR) A Simple Framework for Contrastive Learning of Visual Representations
• (SimCLR2) Big Self-Supervised Models are Strong Semi-Supervised Learners

INR

Implicit Neural Representation

• (Functa) From data to functa: Your data point is a function and you should treat it like one

SR

Super Resolution

• (GPEN) GAN Prior Embedded Network for Blind Face Restoration in the Wild

Face Recognition

• ArcFace: Additive Angular Margin Loss for Deep Face Recognition
• CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition
• GroupFace: Learning Latent Groups and Constructing Group-based Representations for Face Recognition

Facial Editting

• (STIT) Stitch it in Time: GAN-Based Facial Editing of Real Videos

Talking Head

• (SAFA) SAFA: Structure Aware Face Animation

Face Swapping

• SimSwap: An Efficient Framework For High Fidelity Face Swapping
• HifiFace: 3D Shape and Semantic Prior Guided High Fidelity Face Swapping
• FaceInpainter: High Fidelity Face Adaptation to Heterogeneous Domains
• One Shot Face Swapping on Megapixels
• ShapeEditer: a StyleGAN Encoder for Face Swapping
• FaceController: Controllable Attribute Editing for Face in the Wild
• High-Resolution Neural Face Swapping for Visual Effects
• FSGAN: Subject Agnostic Face Swapping and Reenactment
• FaceShifter: Towards High Fidelity And Occlusion Aware Face Swapping
• Towards Open-Set Identity Preserving Face Synthesis
• RSGAN: Face Swapping and Editing using Face and Hair Representation in Latent Spaces
• FSNet: An Identity-Aware Generative Model for Image-based Face Swapping
• DeepFaceLab: Integrated, flexible and extensible face-swapping framework
• Deepfakes for Medical Video De-Identification: Privacy Protection and Diagnostic Information Preservation
• On Face Segmentation, Face Swapping, and Face Perception
• SMILE
• Smooth-Swap
• FaceSwappingGAN
• SberSwap

Background Editting

• Omnimatte: Associating Objects and Their Effects in Video